a2a-protocol

Reference documentation for the Agent2Agent (A2A) protocol. Use when building A2A servers or clients, configuring Ark A2AServer resources, debugging A2A communication, or answering questions about the A2A specification, Agent Cards, task lifecycle, streaming, extensions, or protocol bindings.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A strong reference skill body: tightly organized, with tabular file indexes, a question-to-file lookup guide, and excellent progressive disclosure that points one level deep to verified reference files. The only notable improvement is trimming the small overlap between the inline 'Protocol overview' and the dedicated key-concepts reference.

Suggestions

Trim or shorten the 'Protocol overview' section to avoid duplicating content already covered in topic-key-concepts.md and spec-02-core-concepts.md, or replace it with a one-line pointer to those files.

Consider adding a one-line note in the JSON-RPC methods table or quick-lookup guide clarifying which methods require streaming/push-notification setup, to make the lookup guide even more directly actionable.

Dimension	Reasoning	Score
Conciseness	Lean and well-organized with no padding of basic concepts; the inline 'Protocol overview' slightly duplicates content already present in topic-key-concepts.md / spec-02-core-concepts.md, which is the main reason it is not a 5.	4 / 5
Actionability	Spec/topic reference tables and a 'Quick lookup guide' mapping common questions to specific files give concrete navigation, and the Agent Card JSON example is copy-paste-ready; no executable commands, but that is inherent to a reference skill rather than a gap.	4 / 5
Workflow Clarity	Clear decision flow for which reference to open — 'When to use', a quick-lookup guide, and explicit v0.3-vs-v1.0 defaulting guidance ('Use v0.3 by default… only consult v1.0 when…'); no destructive/batch workflow so the destructive-cap does not apply, and no validation steps are needed for a pure reference.	4 / 5
Progressive Disclosure	Exemplary one-level-deep structure: a concise overview in SKILL.md with two organized reference tables (spec sections, topic guides), a quick-lookup map, and clear version scoping; all referenced files (spec-01..11, topic-*.md, v1.0-rc/topic-whats-new-v1.md) verified to exist.	5 / 5
	Total	17 / 20 Passed

Description

88%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-crafted reference-skill description: it concisely states the domain and purpose, provides an explicit 'Use when…' trigger list spanning the major subtopics, and stays largely distinct from neighboring skills. Minor additions of synonyms ('agent-to-agent', 'A2A SDK') would push trigger quality to the top anchor.

Dimension	Reasoning	Score
Specificity	Names the A2A domain and lists multiple concrete actions across sub-areas — building servers/clients, configuring Ark A2AServer resources, debugging communication, and answering questions about the spec, Agent Cards, task lifecycle, streaming, extensions, and protocol bindings — giving comprehensive coverage.	5 / 5
Completeness	Clearly states what ('Reference documentation for the Agent2Agent (A2A) protocol') and an explicit 'Use when…' clause with concrete trigger phrases, answering both what and when.	5 / 5
Trigger Term Quality	Strong natural terms a developer would say ('building A2A servers or clients', 'debugging A2A communication', 'Agent Cards', 'task lifecycle', 'streaming', 'extensions'); a few synonyms like 'agent-to-agent' or 'A2A SDK' are absent, keeping it just below a 5.	4 / 5
Distinctiveness Conflict Risk	A distinct niche (A2A protocol, Agent Cards, Ark A2AServer) with triggers unlikely to fire for unrelated skills; minor conceptual adjacency to MCP/agent-streaming topics keeps it from a 5.	4 / 5
	Total	18 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
relative_links	Relative link issues: 32 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: mckinsey/agents-at-scale-ark
Path: .claude/skills/a2a-protocol/SKILL.md
Commit: b018d5b

Reviewed: 12 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.